|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Deep Imitation Learning for Autonomous Vehicles Based on Convolutional Neural Networks显示文摘Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes. | Parham M.Kebria Abbas Khosravi Syed Moshfeq Salaken Saeid Nahavandi | 2020 | IEEE/CAA Journal of Automatica Sinica2020，7，1： | 6 |
| 2 | Exploration of the shared pathophysiological mechanisms of gestational diabetes and large for gestational age offspring显示文摘Gestational diabetes mellitus (GDM) and large for gestational age (LGA) offspring are two common pregnancy complications. Connections also exist between the two conditions, including mutual maternal risk factors for the conditions and an increased prevalence of LGA offspring amongst pregnancies affected by GDM. Thus, it is important to elucidate potential shared underlying mechanisms of both LGA and GDM. One potential mechanistic link relates to macronutrient metabolism. Indeed, derangement of carbohydrate and lipid metabolism is present in GDM, and maternal biomarkers of glucose and lipid control are associated with LGA neonates in such pregnancies. The aim of this paper is therefore to reflect on the existing nutritional guidelines for GDM in light of our understanding of the pathophysiological mechanisms of GDM and LGA offspring. Lifestyle modification is first line treatment for GDM, and while there is some promise that nutritional interventions may favourably impact outcomes, there is a lack of definitive evidence that changing the macronutrient composition of the diet reduces the incidence of either GDM or LGA offspring. The quality of the available evidence is a major issue, and rigorous trials are needed to inform evidence-based treatment guidelines. | Sofia Nahavandi Sarah Price Priya Sumithran Elif Ilhan Ekinci | 2019 | World Journal of Diabetes2019，10，6： | 5 |
| 3 | Comments on' Information measure for performance of image fusion' 显示文摘 | Hossny M Nahavandi S Creighton D | 2008 | Electronics letters2008，44，18： | 1 |
| 4 | Recognition of Moving Ground Targets by Measuring and Processing Seismic Signal显示文摘 | Jinhui Lan Saeid Nahavandi Tian Lan | 2005 | Measurement2005，37，： | 1 |
| 5 | Constructionof optimal prediction intervals for load forecasting problems 显示文摘 | KHOSRAVI A’NAHAVANDI S CREIGHTON D | 2010 | IEEE Trans on Power Systems2010，25，3： | 1 |
| 6 | Lower upper bound estimation method for construction of neural network- based prediction intervals显示文摘 | Khosravi A Nahavandi S Creighton D | 2011 | Neural Networks IEEE Transac- tions on2011，22，3： | 1 |
| 7 | Multichannel Biomedical Time Series Clustering via Hierarchical Probabilistic Latent Semantic Analysis 显示文摘 | Wang J Sun X P Nahavandi S | 2014 | Computer Methods and Programs in Biomedicine2014，117，2： | 1 |
| 8 | A prediction interval- based approach to determine optimal structures of neural network metamodels 显示文摘 | Khosravi A Nahavandi S Creighton D | 2010 | Expert systems with applications2010，37，3： | 1 |
| 9 | Robust finite-hori- zon Kalman filter for uncertain discrete-time sys- tems 显示文摘 | Mohamed S M K Nahavandi S | 2012 | IEEE Transactions on Automatic Con- trol2012，57，6： | 1 |
| 10 | A lower-upper bound estimation method for construction of neuralnetwork based prediction intervals显示文摘 | KHOSRAVI A'NAHAVANDI S'CREIGHTON D' | 2011 | IEEE Trans on NeuralNetwork2011，22，3： | 1 |
| 11 | A case for an international consortium on system -of-systems engineering显示文摘 | D De Laurentis C Dickerson M DiMario P Gartz M M Jamshidi S Nahavandi A P Sage E B Sloane | 2007 | IEEE Systems Journal2007，1，1： | 1 |
| 12 | Intervaltype-2 fuzzy logic systems for load forecasting:a comparativestudy显示文摘 | KHOSRAVI A NAHAVANDI S CREIGHTON D | 2012 | IEEE Trans on Power Systems2012，27，3： | 1 |
| 13 | Dielectrophoretic platforms for bio-microfluidic systems显示文摘 | KHOSHMANESH K NAHAVANDI S BARATCHI S | 2011 | Biosensors and Bioelectronics2011，26，5： | 1 |
| 14 | A non- isolated muhiinput/multioutput DC/DC boostconverter for electric vehicle applications显示文摘 | Nahavandi A Hagh M T Sharifian M B B | 2015 | IEEE Transaction on Power Electronics2015，30，4： | 1 |
| 15 | Asymmetrical three-DOFs rotational-translational parallel-kinematics mechanisms on Lie group theory显示文摘 | Refaat S Herve J M Nahavandi S | 2006 | European Journal of Mechanics-A/Solid2006，25，3： | 1 |
| 16 | SPC01-2:a new blind signal separation algorithm for instantaneous MIMO system,Global Telecommunications Conference,2006,Globecom 06显示文摘 | Gu Nong Guan Zhenying Nahavandi S | | 0，，1： | 1 |
| 17 | Acculturation in Mergers and Acquisitions显示文摘 | Nahavandi A Malekzadeh A R | 1988 | Academy of Management Review1988，13，1： | 1 |
| 18 | Pre- diction Intervals for Short-term Wind Farm Power Genera- tion Forecasts显示文摘 | KHOSRAVI A NAHAVANDI S CREIGHTON D | 2013 | IEEE Transactions on Sustainable Energy2013，4，3： | 1 |
| 19 | Comments on iniormation measure tbr performance of image fusion 显示文摘 | Hossny M Nahavandi S Creighton D | 2008 | Electronics Letters2008，44，18： | 1 |
| 20 | Robust finite horizon kalman filtering for uncertain discrete-time systems显示文摘 | Mohame S M K S Nahavandi | 2012 | IEEE Transactions on Automatic Control2012，57，6： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员